| name | validate-structured-model-output |
| description | Validates JSON or tool-call model outputs without repair, separating parse, schema, supplied-identifier, semantic, replay, and safety failures. Use for first-attempt benchmarks, teacher-label pipelines, and bounded model tool selection. |
Validate Structured Model Output
Treat model output as untrusted input. Preserve raw bytes and validate a normalized copy through ordered gates.
Validation order
- Transport: A native structured response or the required JSON payload exists.
- Parse: Decode exactly once. In acceptance benchmarks, do not extract JSON from prose or retry malformed output.
- Schema: Enforce required fields, types, controlled values, and cardinality.
- Identifiers: Reject unknown, duplicate, overlapping, invented, or off-request IDs.
- Semantics: Reject equivalent choices where distinctness is required and verify classifications against supplied facts.
- Execution: Replay or otherwise validate the selected operation with the deterministic kernel.
- Safety: Reject continuation through terminal, unresolved, random, hidden, or otherwise unsupported effects.
Keep failure categories separate. A parse failure is not an abstention, and a legal identifier is not proof of a safe or useful result.
Validate JSONL ID contracts
Use the bundled validator when each row contains supplied, ranked, and optional alternative IDs:
python scripts/validate_jsonl_outputs.py results.jsonl \
--supplied-field request.planIDs \
--ranked-field response.rankedPlanIDs \
--alternative-field response.alternativePlanIDs \
--max-ranked 3 --output validation-report.json
It checks duplicate IDs within arrays, overlap between ranked and alternatives, unknown IDs, rank length, and alternatives without a ranked selection. Add project validators after this generic layer.
Benchmark discipline
For first-attempt acceptance, generate once and validate without repair, remediation, or deterministic fallback. Test production remediation separately. Persist raw output, normalized output, every gate result, timing, prompt/config revision, and validator revision so failures remain auditable.
